Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-small-ar-en-8khz – AI Model by muhammadaqibali56822 | AlphaNeural AI
You can deploy this model and start earning money today!
muhammadaqibali56822
/
whisper-small-ar-en-8khz
like
0
transformers
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-small
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-small-ar-en-8khz
This model is a fine-tuned version of
openai/whisper-small
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.9852
Wer: 54.5284
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.7467
1.4245
1000
0.9625
60.4056
0.4801
2.8490
2000
0.8610
55.3652
0.2064
4.2735
3000
0.8988
54.1067
0.1257
5.6980
4000
0.9520
54.1603
0.0757
7.1225
5000
0.9852
54.5284
Framework versions
Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 3.0.1
Tokenizers 0.19.1
